© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9706
    Prev
    Next
    INDEX
    Explanations

    keywords associated with impending personnel changes and government operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequences describing future planned actions or events that will happen.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Previous
    -0.86
    Previous
    -0.84
     previous
    -0.82
     PREVIOUS
    -0.77
    previous
    -0.77
    PREVIOUS
    -0.72
     précédent
    -0.69
     précédente
    -0.69
     précédents
    -0.68
     precedenti
    -0.66
    POSITIVE LOGITS
     tomorrow
    2.14
     soon
    2.05
     prochain
    1.80
     next
    1.73
    soon
    1.71
     upcoming
    1.68
     próxima
    1.66
     prossima
    1.66
     amanhã
    1.64
    tomorrow
    1.62
    Activations Density 0.921%

    No Known Activations